no code implementations • NeurIPS Workshop ICBINB 2021 • Iryna Korshunova, Minqi Jiang, Jack Parker-Holder, Tim Rocktäschel, Edward Grefenstette
Prioritized Level Replay (PLR) has been shown to induce adaptive curricula that improve the sample-efficiency and generalization of reinforcement learning policies in environments featuring multiple tasks or levels.
no code implementations • ICML Workshop AML 2021 • Iryna Korshunova, David Stutz, Alexander A. Alemi, Olivia Wiles, Sven Gowal
We study the adversarial robustness of information bottleneck models for classification.
1 code implementation • ICML Workshop LifelongML 2020 • Iryna Korshunova, Jonas Degrave, Joni Dambre, Arthur Gretton, Ferenc Huszar
One recent approach to meta reinforcement learning (meta-RL) is to integrate models for task inference with models for control.
1 code implementation • NeurIPS 2019 • Iryna Korshunova, Hanchen Xiong, Mateusz Fedoryszak, Lucas Theis
We propose logistic LDA, a novel discriminative variant of latent Dirichlet allocation which is easy to apply to arbitrary inputs.
3 code implementations • NeurIPS 2018 • Iryna Korshunova, Jonas Degrave, Ferenc Huszár, Yarin Gal, Arthur Gretton, Joni Dambre
We present a novel model architecture which leverages deep learning tools to perform exact Bayesian inference on sets of high dimensional, complex observations.
2 code implementations • Twitter 2018 • Lucas Theis, Iryna Korshunova, Alykhan Tejani, Ferenc Huszár
Predicting human fixations from images has recently seen large improvements by leveraging deep representations which were pretrained for object recognition.
no code implementations • ICCV 2017 • Iryna Korshunova, Wenzhe Shi, Joni Dambre, Lucas Theis
We consider the problem of face swapping in images, where an input identity is transformed into a target identity while preserving pose, facial expression, and lighting.
2 code implementations • 29 Apr 2016 • Bob L. Sturm, João Felipe Santos, Oded Ben-Tal, Iryna Korshunova
We apply deep learning methods, specifically long short-term memory (LSTM) networks, to music transcription modelling and composition.